Regex: hold the JIT stack in a pthread key and inherit the shared match context

src/traffic_layout/info.cc

@@ -170,6 +170,25 @@ produce_features(bool json)
   print_feature("TS_IP_TRANSPARENT", TS_IP_TRANSPARENT, json);
   print_feature("TS_HAS_128BIT_CAS", TS_HAS_128BIT_CAS, json);
   print_feature("TS_HAS_TESTS", TS_HAS_TESTS, json);
+  // Whether PCRE2 can run a pattern on the just-in-time engine. This is a property of the
+  // PCRE2 that ATS is linked against, not of ATS, and it decides which resource limit a
+  // pathological pattern reaches: the JIT stack, or the interpreter's far larger match,
+  // depth and heap limits, because the interpreter keeps its backtracking frames on the
+  // heap. Tests that assert on one of those limits need to know.
+  //
+  // PCRE2_JIT_TEST_ALLOC (PCRE2 10.45) also confirms the JIT can allocate executable
+  // memory. PCRE2_CONFIG_JIT does not, and reports success on a hardened runtime where
+  // every JIT compile then fails, which is the direction that misleads a test gate.
+  {
+    uint32_t has_jit = 0;
+
+#ifdef PCRE2_JIT_TEST_ALLOC
+    has_jit = pcre2_jit_compile(nullptr, PCRE2_JIT_TEST_ALLOC) == 0;
+#else
+    pcre2_config(PCRE2_CONFIG_JIT, &has_jit);
+#endif
+    print_feature("TS_HAS_PCRE2_JIT", has_jit != 0, json);
+  }
   print_feature("TS_MAX_THREADS_IN_EACH_THREAD_TYPE", TS_MAX_THREADS_IN_EACH_THREAD_TYPE, json);
   print_feature("TS_MAX_NUMBER_EVENT_THREADS", TS_MAX_NUMBER_EVENT_THREADS, json);
   print_feature("TS_MAX_HOST_NAME_LEN", TS_MAX_HOST_NAME_LEN, json);

src/tsutil/Regex.cc

@@ -26,6 +26,7 @@
 
 #define PCRE2_CODE_UNIT_WIDTH 8
 #include <pcre2.h>
+#include <pthread.h>
 
 #include <array>
 #include <vector>
@@ -79,6 +80,63 @@ my_free(void *ptr, void * /*caller*/)
   free(ptr);
 }
 
+//----------------------------------------------------------------------------
+// One match context is shared by every thread that matches through it, and PCRE2
+// requires a distinct JIT stack per thread, so the stack comes from a callback
+// invoked at match time rather than a pointer baked in when the context is built.
+//
+// The per thread stack is held in a pthread key rather than a thread_local. A
+// thread_local with a destructor registers it through __cxa_thread_atexit, which
+// takes the dynamic loader lock; doing that from a match would invert lock order
+// against a dlopen caller running a plugin's static initialization. See the same
+// hazard described at Diags::tag_activated. A pthread key registers its destructor
+// once, at key creation, and never from the matching path.
+pthread_key_t  jit_stack_key;
+bool           jit_stack_key_valid = false;
+pthread_once_t jit_stack_key_once  = PTHREAD_ONCE_INIT;
+
+void
+destroy_jit_stack(void *stack)
+{
+  if (stack != nullptr) {
+    pcre2_jit_stack_free(static_cast<pcre2_jit_stack *>(stack));
+  }
+}
+
+void
+make_jit_stack_key()
+{
+  jit_stack_key_valid = pthread_key_create(&jit_stack_key, destroy_jit_stack) == 0;
+}
+
+pcre2_jit_stack *
+jit_stack_for_this_thread(void *)
+{
+  pthread_once(&jit_stack_key_once, make_jit_stack_key);
+  if (!jit_stack_key_valid) {
+    // Without a key there is nowhere to keep a stack, and jit_stack_key holds a
+    // default value that may name an unrelated key. Returning null tells PCRE2 to
+    // use its own default stack, which pcre2jit documents as thread safe.
+    return nullptr;
+  }
+
+  auto *stack = static_cast<pcre2_jit_stack *>(pthread_getspecific(jit_stack_key));
+  if (stack == nullptr) {
+    // One page to start, one mebibyte at most. The maximum is address space reserved at
+    // creation and made resident only as deep as a match actually goes, so a larger one
+    // costs nothing per match, and a mebibyte already resolves a longer subject than
+    // proxy.config.http.request_header_max_size lets a client send.
+    stack = pcre2_jit_stack_create(4096, 1024 * 1024, nullptr);
+    if (pthread_setspecific(jit_stack_key, stack) != 0) {
+      // Nothing holds the stack now, so it would leak once per match. Give it back and
+      // let PCRE2 use its own default stack for this call.
+      pcre2_jit_stack_free(stack);
+      return nullptr;
+    }
+  }
+  return stack;
+}
+
 //----------------------------------------------------------------------------
 class RegexContext
 {
@@ -100,9 +158,6 @@ class RegexContext
     if (_match_context != nullptr) {
       pcre2_match_context_free(_match_context);
     }
-    if (_jit_stack != nullptr) {
-      pcre2_jit_stack_free(_jit_stack);
-    }
   }
   pcre2_general_context *
   get_general_context()
@@ -126,13 +181,11 @@ class RegexContext
     _general_context = pcre2_general_context_create(my_malloc, my_free, nullptr);
     _compile_context = pcre2_compile_context_create(_general_context);
     _match_context   = pcre2_match_context_create(_general_context);
-    _jit_stack       = pcre2_jit_stack_create(4096, 1024 * 1024, nullptr); // 1 page min and 1MB max
-    pcre2_jit_stack_assign(_match_context, nullptr, _jit_stack);
+    pcre2_jit_stack_assign(_match_context, jit_stack_for_this_thread, nullptr);
   }
   pcre2_general_context *_general_context = nullptr;
   pcre2_compile_context *_compile_context = nullptr;
   pcre2_match_context   *_match_context   = nullptr;
-  pcre2_jit_stack       *_jit_stack       = nullptr;
 };
 
 } // namespace
@@ -257,8 +310,20 @@ struct RegexMatchContext::_MatchContext {
 //----------------------------------------------------------------------------
 RegexMatchContext::RegexMatchContext()
 {
-  auto ctx = pcre2_match_context_create(nullptr);
-  debug_assert_message(ctx, "Failed to allocate custom pcre2 match context");
+  // Copy the shared context rather than building a blank one. A blank context
+  // silently drops everything the shared context configures, which is how this
+  // type came to run with PCRE2's fallback 32KiB JIT stack instead of the 1MiB
+  // one. Callers override only the fields they mean to.
+  //
+  // pcre2_match_context_copy dereferences its argument rather than returning null
+  // for one, and RegexContext's constructor does not check its allocations, so a
+  // shared context that failed to allocate would crash here. Fall back to a blank
+  // context, which is what this constructor built before and which no reader of
+  // _match_context dereferences unchecked.
+  auto *shared = RegexContext::get_instance()->get_match_context();
+  auto *ctx    = shared != nullptr ? pcre2_match_context_copy(shared) : pcre2_match_context_create(nullptr);
+
+  debug_assert_message(ctx, "Failed to obtain a pcre2 match context");
   _MatchContext::set(_match_context, ctx);
 }